Parameter cascading for panel models with unknown number of unobserved factors: An application to the credit spread puzzle

The iterative least squares method for estimating panel models with unobservable factor structure is extended to cover the case where the number of factors is unknown a priori. The proposed estimation algorithm optimizes a penalized least squares objective function to estimate the factor dimension jointly with the remaining model parameters in an iterative hierarchical order. Monte Carlo experiments show that, in many configurations of the data, such a refinement provides more efficient estimates in terms of MSE than those that could be achieved if the feasible iterative least squares estimator is calculated with an externally selected factor dimension. The method is applied to the problem of the credit spread puzzle to estimate the space of the missing risk factors jointly with the effects of the observed credit and illiquidity risks.

[1]  T. Vorst,et al.  Comparing Possible Proxies of Corporate Bond Liquidity , 2003 .

[2]  Eli M. Remolona,et al.  The Credit Spread Puzzle , 2003 .

[3]  M. Hallin,et al.  Determining the Number of Factors in the General Dynamic Factor Model , 2007 .

[4]  J. Bai,et al.  Determining the Number of Factors in Approximate Factor Models , 2000 .

[5]  E. Rossi,et al.  Euro Corporate Bonds Risk Factors , 2013 .

[6]  Josef Lakonishok,et al.  Momentum Strategies , 1995 .

[7]  J. Bai,et al.  Panel Data Models With Interactive Fixed Effects , 2009 .

[8]  J. Stock,et al.  Forecasting Using Principal Components From a Large Number of Predictors , 2002 .

[9]  B. Swaminathan,et al.  Stock and Bond Market Interaction: Does Momentum Spill Over? , 2002 .

[10]  M. Pesaran.  Estimation and Inference in Large Heterogeneous Panels with a Multifactor Error Structure , 2004, SSRN Electronic Journal.

[11]  Estimating the number of common factors in serially dependent approximate factor models , 2012 .

[12]  Hendrik Bessembinder,et al.  Market Transparency, Liquidity Externalities, and Institutional Trading Costs in Corporate Bonds , 2005 .

[13]  A. Onatski.  TESTING HYPOTHESES ABOUT THE NUMBER OF FACTORS IN LARGE FACTOR MODELS , 2009 .

[14]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[15]  Dominik Liebl,et al.  phtt: Panel Data Analysis with Heterogeneous Time Trends in R , 2014 .

[16]  Ronald Smith,et al.  A Principal Components Approach to Cross-Section Dependence in Panels , 2002 .

[17]  Jiguo Cao,et al.  Linear Mixed-Effects Modeling by Parameter Cascading , 2010 .

[18]  Elias Tzavalis,et al.  Testing for unit roots in short panels allowing for a structural break , 2014, Comput. Stat. Data Anal..

[19]  Charles Trzcinka,et al.  A New Estimate of Transaction Costs , 1999 .

[20]  Serena Ng,et al.  Determining the Number of Primitive Shocks in Factor Models , 2007 .

[21]  Seung C. Ahn,et al.  Panel Data Models with Multiple Time-Varying Individual Effects , 2013 .

[22]  Long Chen,et al.  Corporate Bond Liquidity and Its Effect on Bond Yield Spreads , 2003 .

[23]  Yusho Kagraoka.  A time-varying common risk factor affecting corporate yield spreads , 2010 .

[24]  George Kapetanios,et al.  A Testing Procedure for Determining the Number of Factors in Approximate Factor Models With Large Datasets , 2010 .

[25]  Stéphane Dray,et al.  On the number of principal components: A test of dimensionality based on measurements of similarity between matrices , 2008, Comput. Stat. Data Anal..

[26]  Dominik Liebl,et al.  The R-package phtt: Panel Data Analysis with Heterogeneous Time Trends , 2014, 1407.6484.

[27]  P. Collin‐Dufresne,et al.  The Determinants of Credit Spread Changes , 2001 .

[28]  Hendrik Bessembinder,et al.  Optimal Market Transparency : Evidence from the Initiation of Trade Reporting in Corporate Bonds * , 2005 .

[29]  Christopher J. Sullivan.  Corporate Yield Spreads: Default Risk or Liquidity? New Evidence from the Credit Default Swap Market , 2006 .

[30]  Jushan Bai,et al.  Estimating cross-section common stochastic trends in nonstationary panel data , 2004 .

[31]  Julie Josse,et al.  Selecting the number of components in principal component analysis using cross-validation approximations , 2012, Comput. Stat. Data Anal..

[32]  Hsin-Cheng Huang,et al.  A new approach for selecting the number of factors , 2010, Comput. Stat. Data Anal..

[33]  A. Onatski.  Determining the Number of Factors from Empirical Distribution of Eigenvalues , 2010, The Review of Economics and Statistics.

[34]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[35]  Narasimhan Jegadeesh,et al.  Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency , 1993 .

[36]  Robin C. Sickles,et al.  A NEW PANEL DATA TREATMENT FOR HETEROGENEITY IN TIME TRENDS , 2012, Econometric Theory.

[37]  E. Elton,et al.  Explaining the Rate Spread on Corporate Bonds , 1999 .

[38]  Ming Huang,et al.  How Much of Corporate-Treasury Yield Spread is Due to Credit Risk? , 2002 .

[39]  Elias Tzavalis,et al.  Detection of structural breaks in linear dynamic panel data models , 2012, Comput. Stat. Data Anal..

[40]  A. Onatski.  Asymptotics of the principal components estimator of large factor models with weakly influential factors , 2012 .

[41]  Serena Ng,et al.  Panel cointegration with global stochastic trends , 2008, 0805.1768.

[42]  A. Freeman,et al.  Bond Liquidity Estimation and the Liquidity Effect in Yield Spreads , 2002 .